CIS 5590.004. Artificial General Intelligence

Concept and Learning

1. Models of Concept

Categorization:

Classical view: definition, necessary and sufficient condition
Prototype theory and Exemplar theory
Concept hierarchy and taxonomies, basic-level concepts

Semantic networks / Conceptual graphs / Knowledge graphs (as models of the mind) vs. (artificial) neural networks (as models of the brain)

Conceptual Space and Semantic Space

"Grandmother cell" vs. Ensemble coding

Compositionality in languages and neural-nets, Conceptual blending, Tensor product variable binding

2. Models of Learning

What is learned:

A conceptual relation: supervised learning, end-to-end training of a universal function approximator
A classification: unsupervised learning, clustering, associative memory

3. Set-Theoretic Inference Rules in NAL

Concept model: extension and intension, graded and dynamic, empirical and analytical
Conceptual graph, copulas, boundaries
Compound terms and concept construction
Learning as reasoning, multi-strategies

Reading

Non-Axiomatic Logic: A Model of Intelligent Reasoning, 2nd Edition, Chapters 6-8